Multiprocessing bug on macOS
- Dominant language
- Python
- Stars
- 11.7k
- Forks
- 920
- PR merge metrics
- No merged PRs in 30d
Description
macOS 12.1 (on Intel hardware) + Python 3.9.10, cleanlab 3f17be685e3c38e7a97737d083507b56b1ec897f. Running the code below causes an infinite loop of exceptions.
To reproduce, save this as `bug.py` and run it:
```python
import numpy as np
from cleanlab.count import compute_confident_joint
from cleanlab.filter import find_label_issues
pred_probs = \
np.array(
[[0.8, 0.2],
[0.7, 0.3],
[0.1, 0.9],
[0.3, 0.7]])
labels = np.array([0, 0, 1, 1])
cj = compute_confident_joint(labels, pred_probs, calibrate=False)
print(f'confident joint: {cj}')
issues = find_label_issues(labels, pred_probs)
print(f'label issues: {issues}')
```
Output:
```
confident joint: [[1 0]
[0 1]]
confident joint: [[1 0]
[0 1]]
Traceback (most recent call last):
File "", line 1, in
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py", line 116, in spawn_main
exitcode = _main(fd, parent_sentinel)
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py", line 125, in _main
prepare(preparation_data)
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py", line 236, in prepare
_fixup_main_from_path(data['init_main_from_path'])
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py", line 287, in _fixup_main_from_path
main_content = runpy.run_path(main_path,
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/runpy.py", line 268, in run_path
return _run_module_code(code, init_globals, run_name,
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/runpy.py", line 97, in _run_module_code
_run_code(code, mod_globals, init_globals,
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/Users/anish/src/bug.py", line 16, in
issues = find_label_issues(labels, pred_probs)
File "/Users/anish/src/cleanlab/cleanlab/filter.py", line 524, in find_label_issues
with multiprocessing.Pool(
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/context.py", line 119, in Pool
return Pool(processes, initializer, initargs, maxtasksperchild,
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/pool.py", line 212, in __init__
self._repopulate_pool()
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/pool.py", line 303, in _repopulate_pool
return self._repopulate_pool_static(self._ctx, self.Process,
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/pool.py", line 326, in _repopulate_pool_static
w.start()
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/process.py", line 121, in start
self._popen = self._Popen(self)
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/context.py", line 284, in _Popen
return Popen(process_obj)
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/popen_spawn_posix.py", line 32, in __init__
super().__init__(process_obj)
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/popen_fork.py", line 19, in __init__
self._launch(process_obj)
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/popen_spawn_posix.py", line 42, in _launch
prep_data = spawn.get_preparation_data(process_obj._name)
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py", line 154, in get_preparation_data
_check_not_importing_main()
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py", line 134, in _check_not_importing_main
raise RuntimeError('''
RuntimeError:
An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.
This probably means that you are not using fork to start your
child processes and you have forgotten to use the proper idiom
in the main module:
if __name__ == '__main__':
freeze_support()
...
The "freeze_support()" line can be omitted if the program
is not going to be frozen to produce an executable.
confident joint: [[1 0]
[0 1]]
Traceback (most recent call last):
File "", line 1, in
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py", line 116, in spawn_main
exitcode = _main(fd, parent_sentinel)
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py", line 125, in _main
prepare(preparation_data)
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py", line 236, in prepare
_fixup_main_from_path(data['init_main_from_path'])
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py", line 287, in _fixup_main_from_path
main_content = runpy.run_path(main_path,
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/runpy.py", line 268, in run_path
return _run_module_code(code, init_globals, run_name,
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/runpy.py", line 97, in _run_module_code
_run_code(code, mod_globals, init_globals,
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/Users/anish/src/bug.py", line 16, in
issues = find_label_issues(labels, pred_probs)
File "/Users/anish/src/cleanlab/cleanlab/filter.py", line 524, in find_label_issues
with multiprocessing.Pool(
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/context.py", line 119, in Pool
return Pool(processes, initializer, initargs, maxtasksperchild,
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/pool.py", line 212, in __init__
self._repopulate_pool()
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/pool.py", line 303, in _repopulate_pool
return self._repopulate_pool_static(self._ctx, self.Process,
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/pool.py", line 326, in _repopulate_pool_static
w.start()
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/process.py", line 121, in start
self._popen = self._Popen(self)
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/context.py", line 284, in _Popen
return Popen(process_obj)
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/popen_spawn_posix.py", line 32, in __init__
super().__init__(process_obj)
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/popen_fork.py", line 19, in __init__
self._launch(process_obj)
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/popen_spawn_posix.py", line 42, in _launch
prep_data = spawn.get_preparation_data(process_obj._name)
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py", line 154, in get_preparation_data
_check_not_importing_main()
File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py", line 134, in _check_not_importing_main
raise RuntimeError('''
RuntimeError:
An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.
This probably means that you are not using fork to start your
child processes and you have forgotten to use the proper idiom
in the main module:
if __name__ == '__main__':
freeze_support()
...
The "freeze_support()" line can be omitted if the program
is not going to be frozen to produce an executable.
...
```
On a different platform (Debian 10, Linux 4.19.0-11-amd64, Python 3.7.3), this bug does not occur, and running the code produces the expected output:
```
confident joint: [[1 0]
[0 1]]
label issues: [False False False False]
```
The user can work around the issue with the following, but we should fix cleanlab so that the above version of the code works.
```python
import numpy as np
from cleanlab.count import compute_confident_joint
from cleanlab.filter import find_label_issues
def main():
pred_probs = \
np.array(
[[0.8, 0.2],
[0.7, 0.3],
[0.1, 0.9],
[0.3, 0.7]])
labels = np.array([0, 0, 1, 1])
cj = compute_confident_joint(labels, pred_probs, calibrate=False)
print(f'confident joint: {cj}')
issues = find_label_issues(labels, pred_probs)
print(f'label issues: {issues}')
if __name__ == '__main__':
main()
```
This code produces the expected output on macOS.
Contributor guide
Assessment
This issue has not been assessed yet.